Talk to Your Documents, Powered by Llama-Index

In this video, we will build a Chat with your document system using Llama-Index. I will explain concepts related to llama index with a focus on understanding Vector Store Index.

▬▬▬▬▬▬▬▬▬▬▬▬▬▬ CONNECT ▬▬▬▬▬▬▬▬▬▬▬
☕ Buy me a Coffee: ko-fi.com/promptengineering
|🔴 Support my work on Patreon: Patreon.com/PromptEngineering
🦾 Discord: discord.com/invite/t4eYQRUcXB
▶️️ Subscribe: youtube.com/@engineerprompt?sub_confirmation=1
📧 Business Contact: engineerprompt@gmail.com
💼Consulting: calendly.com/engineerprompt/consulting-call
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬
LINKS:
Google Colab: tinyurl.com/hms9c4jv
llama-Index Github: github.com/jerryjliu/llama_index
▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬▬

Timestamps:
[00:00] What is Llama-index
[01:10] System Architecture
[02:54] Llama-index Setup
[04:54] Loading Documents
[05:42] Creating the Vector Store Index
[06:16] Creating Query Engine
[07:06] Q&A Over Documents
[09:00] How to Persist the Index
[10:20] What is inside the Index?
[11:38] How to change the default LLM
[13:25] Change the Chunk Size
[14:26] Use Open Source LLM with Llama I